© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13048
    Prev
    Next
    INDEX
    Explanations

    length and domain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eyeb
    -0.07
    ç²īçļĦ
    -0.07
    çIJĨçĶ±
    -0.07
    èĤīçľ¼
    -0.07
    dens
    -0.06
    强度çļĦ
    -0.06
    elte
    -0.06
    aih
    -0.06
    ä¸ĸçķĮåĨłåĨĽ
    -0.06
    éľ²æ°´
    -0.06
    POSITIVE LOGITS
    éķ¿åº¦ä¸º
    0.09
     length
    0.08
    åĨħè¿Ľè¡Į
    0.08
    éķ¿ä¸º
    0.08
    Length
    0.08
    éķ¿åº¦
    0.08
     Length
    0.08
    length
    0.08
     lengths
    0.07
     Vide
    0.07
    Activations Density 0.012%

    No Known Activations